© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 4024
    Prev
    Next
    INDEX
    Explanations

    programmed safe guard response

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hänen
    1.52
     ettiği
    1.48
     často
    1.42
     말미암
    1.41
    넬
    1.36
    Malley
    1.36
    เกี่ยวข้อง
    1.35
     봐야
    1.34
    RELATES
    1.34
     amiss
    1.34
    POSITIVE LOGITS
     hope
    1.82
     hopes
    1.79
     beginners
    1.79
     started
    1.78
    浮
    1.77
     Liqu
    1.75
    started
    1.72
     thankful
    1.71
     crowdfunding
    1.68
    decimals
    1.66
    Activations Density 0.151%

    No Known Activations